<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
distilbert-base-uncased-finetuned-amazon-fine-food-lite
This model is a fine-tuned version of distilbert-base-uncased on an lite-version of the Amazon fine food Review dataset. It achieves the following results on the evaluation set:
- Loss: 0.8019
- Accuracy: 0.8097
- F1: 0.8286
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 0.41 | 100 | 0.6570 | 0.7479 | 0.7815 |
| No log | 0.82 | 200 | 0.5237 | 0.7914 | 0.8213 |
| 0.7333 | 1.23 | 300 | 0.5004 | 0.8042 | 0.8343 |
| 0.7333 | 1.65 | 400 | 0.5946 | 0.7715 | 0.8107 |
| 0.4693 | 2.06 | 500 | 0.5146 | 0.8124 | 0.8355 |
| 0.4693 | 2.47 | 600 | 0.5877 | 0.7950 | 0.8231 |
| 0.4693 | 2.88 | 700 | 0.6603 | 0.7855 | 0.8177 |
| 0.3151 | 3.29 | 800 | 0.5712 | 0.8150 | 0.8365 |
| 0.3151 | 3.7 | 900 | 0.6085 | 0.8081 | 0.8335 |
| 0.208 | 4.12 | 1000 | 0.7475 | 0.7807 | 0.8151 |
| 0.208 | 4.53 | 1100 | 0.6621 | 0.8214 | 0.8435 |
| 0.208 | 4.94 | 1200 | 0.6542 | 0.8229 | 0.8425 |
| 0.1479 | 5.35 | 1300 | 0.7987 | 0.7948 | 0.8229 |
| 0.1479 | 5.76 | 1400 | 0.7361 | 0.8118 | 0.8346 |
| 0.1 | 6.17 | 1500 | 0.8019 | 0.8097 | 0.8286 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Tokenizers 0.13.3
